From cef832ecb025924cb506ddd0ad6da4852deef5c8 Mon Sep 17 00:00:00 2001 From: zefie Date: Wed, 4 Nov 2026 16:53:35 -0500 Subject: [PATCH] update readme --- README.md | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 879031d..71988d0 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,8 @@ -Convert-to-Quant (`ctq`) is installed for normal quantizations. -`hf`, the Hugging Face CLI command, and llama.cpp's compiled binaries are also available. +These scripts require [llama.cpp](https://github.com/ggml-org/llama.cpp) and [Convert-to-Quant](https://github.com/silveroxides/convert_to_quant). -For GGUF quantizations, try: +`hf`, the Hugging Face CLI command is also suggested, but not required. + +For quantizations or conversions, try: - `hf_to_nvfp4_quant` (huggingface structure to GGUF) - `gguf_to_nvfp4_quant` (GGUF to GGUF) - `safetensors_to_nvfp4_quant` (ComfyUI style safetensors to GGUF (untested)) @@ -26,3 +27,5 @@ The same directory can be quantized to one ComfyUI NVFP4 safetensors file: `hf_to_nvfp4_safetensors -o gemma-4-12B-it-heretic-NVFP4.safetensors gemma-4-12B-it-heretic` Conversions between formats without quantization is available in the custom commands with `--no-quant`. + +Currently the only supported modes are "Quantize to NVFP4" or "Copy without quantizing" (`--no-quant`). I may add other quantization options in the future.